Pith. sign in

REVIEW 15 cited by

XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.21416 v1 pith:RWUHUIUD submitted 2025-06-26 cs.CV

classification cs.CV
keywords controlxverseattributesgenerationmulti-subjectsemanticsubjectidentity
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Achieving fine-grained control over subject identity and semantic attributes (pose, style, lighting) in text-to-image generation, particularly for multiple subjects, often undermines the editability and coherence of Diffusion Transformers (DiTs). Many approaches introduce artifacts or suffer from attribute entanglement. To overcome these challenges, we propose a novel multi-subject controlled generation model XVerse. By transforming reference images into offsets for token-specific text-stream modulation, XVerse allows for precise and independent control for specific subject without disrupting image latents or features. Consequently, XVerse offers high-fidelity, editable multi-subject image synthesis with robust control over individual subject characteristics and semantic attributes. This advancement significantly improves personalized and complex scene generation capabilities.

Discussion (0). Sign in to comment.

Forward citations

Cited by 15 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation

    cs.CV 2025-12 unverdicted novelty 7.0 of 10

    InstructMoLE replaces per-token routing with instruction-guided global routing for mixture-of-low-rank-experts in diffusion transformers and adds an output-space orthogonality loss to improve multi-conditional image g...

  2. MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement

    cs.CV 2025-09 conditional novelty 7.0 of 10

    MOSAIC improves multi-subject personalized image generation by supervising attention maps with semantic point correspondences and a disentanglement loss, and introduces the SemAlign-MS dataset for training.

  3. MIBE: Multi-subject Interaction Benchmark and Evaluator for Personalized Image Generation

    cs.CV 2026-07 unverdicted novelty 6.0 of 10

    MIBE introduces a multi-subject interaction benchmark (MIB) with silver and gold sets and a dual-head evaluator (MIE) trained on VLM labels that outperforms baselines in matching human judgments.

  4. Scaling Multi-Reference Image Generation with Dynamic Reward Optimization

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    Introduces OmniRef-Bench benchmark and DyRef two-stage framework using Difficulty-aware Advantage Reweighting and Discriminative Reward Scaling to improve open-source models on complex multi-reference image generation.

  5. Training-Free Image Editing with Visual Context Integration and Concept Alignment

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    VicoEdit performs training-free image editing by transforming source images directly with visual context and concept-alignment-guided posterior sampling, outperforming training-based methods.

  6. Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation

    cs.CV 2026-03 unverdicted novelty 6.0 of 10

    Premier learns user-specific embeddings to modulate text-to-image generation, outperforming prior methods on preference alignment, text consistency, and expert ratings even with limited history.

  7. Hierarchical Concept-to-Appearance Guidance for Multi-Subject Image Generation

    cs.CV 2026-02 conditional novelty 6.0 of 10

    A diffusion-transformer framework with VLM-grounded masked attention and VAE dropout improves identity and prompt fidelity for multi-subject image generation.

  8. Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling

    cs.CV 2025-12 conditional novelty 6.0 of 10

    Scone adds a semantic-bridge attention-masking step to a unified understanding-generation model, improving subject distinction in multi-candidate reference images, and introduces the SconeEval benchmark.

  9. Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling

    cs.CV 2025-12 conditional novelty 6.0 of 10

    Scone unifies subject understanding and generation in a two-stage trained model to improve both composition and distinction in multi-subject image generation, outperforming prior open-source models on new benchmarks.

  10. Adversarial Concept Distillation for One-Step Diffusion Personalization

    cs.CV 2025-10 unverdicted novelty 6.0 of 10

    OPAD enables reliable high-quality personalization of one-step diffusion models via multi-step teacher distillation combined with adversarial alignment losses.

  11. UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A reinforcement-learning reward based on bipartite face matching improves multi-identity consistency and reduces identity confusion in image customization models.

  12. FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus

    cs.CV 2025-09 conditional novelty 6.0 of 10

    FocusDPO adds dynamic spatial weighting to preference-based fine-tuning, improving subject fidelity and reducing attribute leakage in multi-subject personalized image generation.

  13. PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards

    cs.CV 2025-12 conditional novelty 5.0 of 10

    A data-generation pipeline plus pairwise subject-consistency rewards in RL improve consistency and prompt adherence for multi-subject personalized image generation.

  14. UniVerse: A Unified Modulation Framework for Segmentation-Free,Disentangled Multi-Concept Personalization

    cs.CV 2026-05 unverdicted novelty 4.0 of 10

    UniVerse proposes a unified modulation framework for segmentation-free, disentangled multi-concept personalization in diffusion transformers, claiming superior localization and fidelity over baselines.

  15. EditIDv2: Editable ID Customization with Data-Lubricated ID Feature Integration for Text-to-Image Generation

    cs.CV 2025-09 reject novelty 3.0 of 10

    EditIDv2 fine-tunes only PerceiverAttention cross-attention weights on 3K images to inject editability into Flux-based ID customization, reporting selective gains on the self-proposed IBench benchmark.

Pith tools